INDEX

Explanations

terms related to programming constructs and data structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ichten

-0.18

æŁĦ

-0.17

iami

-0.16

ritis

-0.15

\admin

-0.15

loh

-0.15

ì§Ŀ

-0.15

/operators

-0.15

elfth

-0.14

ercul

-0.14

POSITIVE LOGITS

ERSION

0.17

ardi

0.15

INC

0.14

owi

0.14

 vital

0.14

uting

0.13

ac

0.13

 Stop

0.13

lest

0.13

Activations Density 0.002%

terms related to programming constructs and data structures

No Comments

No Known Activations